{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N6BRS5NQNVT4QIBM3CVEQ5XFRS","short_pith_number":"pith:N6BRS5NQ","canonical_record":{"source":{"id":"2401.06603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T14:35:57Z","cross_cats_sorted":[],"title_canon_sha256":"df24fcf0f990eba4f8555d0f2ab7b369dec821232bc408ab5b98b66e446534ad","abstract_canon_sha256":"0d0fbf87970b1f2993677d46176a1056eb01e45ae97a041aeff2356daf61dd37"},"schema_version":"1.0"},"canonical_sha256":"6f831975b06d67c8202cd8aa4876e58c994a863126f93a2137ca0c97f63c8395","source":{"kind":"arxiv","id":"2401.06603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06603","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06603v2","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06603","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"N6BRS5NQNVT4","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"N6BRS5NQNVT4QIBM","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"N6BRS5NQ","created_at":"2026-07-05T10:21:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N6BRS5NQNVT4QIBM3CVEQ5XFRS","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T14:35:57Z","cross_cats_sorted":[],"title_canon_sha256":"df24fcf0f990eba4f8555d0f2ab7b369dec821232bc408ab5b98b66e446534ad","abstract_canon_sha256":"0d0fbf87970b1f2993677d46176a1056eb01e45ae97a041aeff2356daf61dd37"},"schema_version":"1.0"},"canonical_sha256":"6f831975b06d67c8202cd8aa4876e58c994a863126f93a2137ca0c97f63c8395","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:57.070121Z","signature_b64":"6CRcE/9U8SwQgM2tZbZREKfsHWiwV1FV81i21negzASaBUzbuou0oikBzuf7N6fM0A/3LB956cK6HcPYUj0VCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f831975b06d67c8202cd8aa4876e58c994a863126f93a2137ca0c97f63c8395","last_reissued_at":"2026-07-05T10:21:57.069654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:57.069654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06603","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOhiI0eJknmUemNdj6KEP8O4LYwUm/cGxKyNfcXY2UBGNTA8B/LOp9C0dh25i62CNqkNPEb6KRHttI9dqD58Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:36:43.355443Z"},"content_sha256":"8fce44887bc79e966ab9d41501faac293e6283d68ab1e020731ae6d6ee13a37a","schema_version":"1.0","event_id":"sha256:8fce44887bc79e966ab9d41501faac293e6283d68ab1e020731ae6d6ee13a37a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N6BRS5NQNVT4QIBM3CVEQ5XFRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shangding Gu","submitted_at":"2024-01-12T14:35:57Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities for reinforcement learning (RL) models, such as planning and reasoning capabilities. However, the problems of LLMs and RL model collaboration still need to be solved. In this study, we employ a teacher-student learning framework to tackle these problems, specifically by offering feedback for LLMs using RL models and providing high-level information for RL models with LLMs in a cooperative multi-agent setting. Within this framework, the LLM acts as a teacher, while the RL model acts as a student. The two agents cooperatively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06603","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.06603/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jHJT+lhhEYcC0+yNSnObvLWIJBm0tryzx9IC28i2e4lbhPE4lE7NZ0H5dHhAi9ZBFKTpMXr8e6e2IWwzUYhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:36:43.356380Z"},"content_sha256":"62e16d8d8c76d8e7930a3ef377f058c1c9c86ab4a461e3ac9d01b033852a7361","schema_version":"1.0","event_id":"sha256:62e16d8d8c76d8e7930a3ef377f058c1c9c86ab4a461e3ac9d01b033852a7361"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/bundle.json","state_url":"https://pith.science/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T08:36:43Z","links":{"resolver":"https://pith.science/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS","bundle":"https://pith.science/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/bundle.json","state":"https://pith.science/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6BRS5NQNVT4QIBM3CVEQ5XFRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6BRS5NQNVT4QIBM3CVEQ5XFRS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0d0fbf87970b1f2993677d46176a1056eb01e45ae97a041aeff2356daf61dd37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T14:35:57Z","title_canon_sha256":"df24fcf0f990eba4f8555d0f2ab7b369dec821232bc408ab5b98b66e446534ad"},"schema_version":"1.0","source":{"id":"2401.06603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06603","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06603v2","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06603","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"N6BRS5NQNVT4","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"N6BRS5NQNVT4QIBM","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"N6BRS5NQ","created_at":"2026-07-05T10:21:57Z"}],"graph_snapshots":[{"event_id":"sha256:62e16d8d8c76d8e7930a3ef377f058c1c9c86ab4a461e3ac9d01b033852a7361","target":"graph","created_at":"2026-07-05T10:21:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.06603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities for reinforcement learning (RL) models, such as planning and reasoning capabilities. However, the problems of LLMs and RL model collaboration still need to be solved. In this study, we employ a teacher-student learning framework to tackle these problems, specifically by offering feedback for LLMs using RL models and providing high-level information for RL models with LLMs in a cooperative multi-agent setting. Within this framework, the LLM acts as a teacher, while the RL model acts as a student. The two agents cooperatively","authors_text":"Shangding Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T14:35:57Z","title":"Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06603","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8fce44887bc79e966ab9d41501faac293e6283d68ab1e020731ae6d6ee13a37a","target":"record","created_at":"2026-07-05T10:21:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0d0fbf87970b1f2993677d46176a1056eb01e45ae97a041aeff2356daf61dd37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T14:35:57Z","title_canon_sha256":"df24fcf0f990eba4f8555d0f2ab7b369dec821232bc408ab5b98b66e446534ad"},"schema_version":"1.0","source":{"id":"2401.06603","kind":"arxiv","version":2}},"canonical_sha256":"6f831975b06d67c8202cd8aa4876e58c994a863126f93a2137ca0c97f63c8395","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f831975b06d67c8202cd8aa4876e58c994a863126f93a2137ca0c97f63c8395","first_computed_at":"2026-07-05T10:21:57.069654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:57.069654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6CRcE/9U8SwQgM2tZbZREKfsHWiwV1FV81i21negzASaBUzbuou0oikBzuf7N6fM0A/3LB956cK6HcPYUj0VCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:57.070121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fce44887bc79e966ab9d41501faac293e6283d68ab1e020731ae6d6ee13a37a","sha256:62e16d8d8c76d8e7930a3ef377f058c1c9c86ab4a461e3ac9d01b033852a7361"],"state_sha256":"cff52ab4fcfec4774f935bad35c17353be3443682d25487947c59be689bd4607"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sO+LARItMbh9f+/Ro3v5Qyg1QUdm/eFSxuKMgmnmDhqA07HUV2/An8k5o2CjbsHw88Jv9Ewr6Knj7wiXjlYTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:36:43.363274Z","bundle_sha256":"febd4e44656895b4fb82e024396b75c87866fa4c696bbc621f1631d40f01fb7a"}}